CN113229826B - QRS wave detection method and device and electronic equipment - Google Patents
QRS wave detection method and device and electronic equipment Download PDFInfo
- Publication number
- CN113229826B CN113229826B CN202011339363.XA CN202011339363A CN113229826B CN 113229826 B CN113229826 B CN 113229826B CN 202011339363 A CN202011339363 A CN 202011339363A CN 113229826 B CN113229826 B CN 113229826B
- Authority
- CN
- China
- Prior art keywords
- wavelet
- signal
- signals
- detected
- decomposition
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The application discloses a QRS wave detection method device and electronic equipment, wherein the method comprises the following steps: clustering wavelet signals at each position to be detected in the electrocardiosignals to be detected to obtain a plurality of wavelet sets; under the condition that the number of the wavelet sets is two, performing signal decomposition on each wavelet signal in the two wavelet sets to obtain a wavelet signal after signal decomposition; determining a target detection threshold based on the decomposed wavelet signals; and detecting each decomposed wavelet signal based on the target detection threshold value to determine a target QRS wave. This application is through clustering the QRS ripples that detects in advance, then carries out signal decomposition to two kinds of signals that the cluster obtained to the redetermination detects the threshold value, and then can carry out further detection to the QRS ripples that detects in advance to accurate target QRS ripples and interference wave of confirming in the QRS ripples that detects in advance, improved the rate of accuracy that QRS ripples detected.
Description
Technical Field
The application relates to the technical field of electrocardiosignal detection, in particular to a QRS wave detection method, a QRS wave detection device and electronic equipment.
Background
The automatic analysis algorithm in the ECG electrocardiosignals can greatly reduce the workload of doctors, improve the working efficiency and is beneficial to non-professionals to monitor the physiological condition of the non-professionals. The basis of the automatic analysis algorithm is to be able to detect QRS waves accurately. For some signals with better signal quality, it is relatively simple to detect QRS waves, and for some QRS waves with poor signal quality, especially QRS wave signals with some high T waves, it is always a difficult point to detect.
The existing QRS wave detection algorithm mainly comprises the steps of carrying out simple signal preprocessing on signals and setting various detection rules to judge QRS waves. The methods have good QRS wave detection effect on some signals with good quality, but are difficult to identify some high and large T waves or T wave signals with the morphology close to the QRS waves, so that the QRS wave detection is not accurate enough.
Disclosure of Invention
An object of the embodiments of the present application is to provide a method and an apparatus for detecting a QRS wave, and an electronic device, for solving the problem that QRS wave detection in the prior art is not accurate enough.
In order to solve the technical problem, the embodiment of the application adopts the following technical scheme: a QRS wave detection method comprises the following steps:
clustering wavelet signals at each position to be detected in the electrocardiosignals to be detected to obtain a plurality of wavelet sets;
under the condition that the number of the wavelet sets is two, performing signal decomposition on each wavelet signal in the two wavelet sets to obtain a wavelet signal after signal decomposition;
determining a target detection threshold based on the decomposed wavelet signals;
and detecting each decomposed wavelet signal based on the target detection threshold value to determine a target QRS wave.
Optionally, before performing clustering processing on the wavelet signals at each position to be detected in the electrocardiographic signals to be detected, the method further includes:
sequentially carrying out filtering processing and differential processing on the original electrocardiosignals to obtain processed electrocardiosignals to be detected;
and carrying out QRS wave pre-detection processing on the electrocardiosignals to be detected based on the initial detection threshold value so as to determine a plurality of positions to be detected.
Optionally, before performing signal decomposition on each wavelet signal in the two wavelet sets, the method further includes:
determining the wavelet signal similarity of the two wavelet sets;
determining a number of decomposition levels for performing signal decomposition based on the wavelet signal similarities.
Optionally, the determining the wavelet signal similarity of the two wavelet sets specifically includes:
respectively calculating signal parameter average values based on signal parameters of all wavelet signals in the wavelet set to obtain average wavelet signals corresponding to the wavelet set;
and calculating signal correlation based on the average wavelet signals corresponding to the wavelet sets to determine the wavelet signal similarity of the two wavelet sets.
Optionally, the signal decomposition is performed on each wavelet signal in the two wavelet sets to obtain a wavelet signal after the signal decomposition, and the method specifically includes:
performing wavelet decomposition processing on the electrocardiosignal to be detected based on the determined decomposition layer number;
and acquiring wavelet signals at each position to be detected in the electrocardiosignals to be detected after wavelet decomposition processing so as to obtain the wavelet signals after signal decomposition.
Optionally, the determining a target detection threshold based on the decomposed wavelet signal specifically includes:
acquiring wavelet signals of each position to be detected in a preset time period from the electrocardiosignals to be detected after signal decomposition processing, and taking the wavelet signals as first wavelet signals;
determining a plurality of wavelet signals meeting a first condition from the first wavelet signals as second wavelet signals;
determining a plurality of wavelet signals meeting a second condition from the first wavelet signals as third wavelet signals;
and calculating and obtaining the target detection threshold value based on each second wavelet signal and each third wavelet signal.
Optionally, the first condition is: sorting the modulus maxima of the first wavelet signals according to a sorting order from large to small, and then sorting the first wavelet signals positioned at the top n;
the second condition is: sorting the modulus maxima of the first wavelet signals according to a sorting order from large to small, and then sorting the first wavelet signals positioned at the back n; wherein n is less than one-half of the total number of the first wavelet signals and n is greater than or equal to 1.
Optionally, in a case that the number of the wavelet sets is 1, the method further includes: determining wavelet signals at each position to be detected as target QRS waves;
in the case that the number of wavelet sets is greater than 2, the method further comprises: and determining the wavelet signals at the positions to be detected as non-QRS waves.
In order to solve the above problem, the present application provides a QRS wave detection device, including:
the clustering module is used for clustering wavelet signals at each position to be detected in the electrocardiosignals to be detected to obtain a plurality of wavelet sets;
the signal decomposition module is used for performing signal decomposition on each wavelet signal in the two wavelet sets under the condition that the number of the wavelet sets is two to obtain a wavelet signal after the signal decomposition;
a determining module for determining a target detection threshold based on the decomposed wavelet signals;
and the detection module is used for detecting each decomposed wavelet signal based on the target detection threshold value to determine a target QRS wave.
In order to solve the above problem, the present application provides an electronic device, at least comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the QRS wave detection method according to any one of the above methods when executing the computer program on the memory.
The method and the device have the advantages that the pre-detected QRS waves are clustered, then the two types of signals obtained by clustering are subjected to signal decomposition, and the detection threshold value is re-determined, so that the pre-detected QRS waves can be further detected, the target QRS waves and the interference waves can be accurately determined from the pre-detected QRS waves, and the QRS wave detection accuracy is improved.
Drawings
FIG. 1 is a schematic waveform diagram of an ECG signal;
FIG. 2 is a schematic waveform diagram of an ECG signal;
fig. 3 is a flowchart of a QRS wave detection method according to an embodiment of the present application;
fig. 4 is a flowchart of a QRS wave detection method according to another embodiment of the present application;
FIG. 5 is a flowchart illustrating the pre-detection process in an embodiment of the present application;
fig. 6 is a flowchart of a QRS wave detection method according to another embodiment of the present application;
FIG. 7(a) is a schematic diagram of a decomposed wavelet signal after a 2-layer decomposition of the wavelet signal in an embodiment of the present application;
FIG. 7(b) is a schematic diagram of a decomposed wavelet signal after 4-layer decomposition of the wavelet signal in the embodiment of the present application;
FIG. 8 is a diagram illustrating QRS wave detection based on a target detection threshold according to the present application;
fig. 9 is a diagram illustrating QRS wave detection using a fixed threshold in the prior art;
fig. 10 is a block diagram of a QRS wave detection apparatus according to another embodiment of the present application.
Detailed Description
Various aspects and features of the present application are described herein with reference to the drawings.
It will be understood that various modifications may be made to the embodiments of the present application. Accordingly, the foregoing description should not be construed as limiting, but merely as exemplifications of embodiments. Those skilled in the art will envision other modifications within the scope and spirit of the application.
The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the application and, together with a general description of the application given above and the detailed description of the embodiments given below, serve to explain the principles of the application.
These and other characteristics of the present application will become apparent from the following description of a preferred form of embodiment, given as a non-limiting example, with reference to the attached drawings.
It is also to be understood that although the present application has been described with reference to some specific examples, those skilled in the art are able to ascertain many other equivalents to the practice of the present application.
The above and other aspects, features and advantages of the present application will become more apparent in view of the following detailed description when taken in conjunction with the accompanying drawings.
Specific embodiments of the present application are described hereinafter with reference to the accompanying drawings; however, it is to be understood that the disclosed embodiments are merely exemplary of the application, which can be embodied in various forms. Well-known and/or repeated functions and constructions are not described in detail to avoid obscuring the application of unnecessary or unnecessary detail. Therefore, specific structural and functional details disclosed herein are not to be interpreted as limiting, but merely as a basis for the claims and as a representative basis for teaching one skilled in the art to variously employ the present application in virtually any appropriately detailed structure.
The description may use the phrases "in one embodiment," "in another embodiment," "in yet another embodiment," or "in other embodiments," which may each refer to one or more of the same or different embodiments in accordance with the application.
In the electrocardiosignal, the peak is the highest QRS wave, the small wave preceding it is the P wave, and the T wave following it. In the actual detection of QRS waves, in addition to the influence of small noise on the detection, T waves have a great influence on the detection of QRS waves, and in addition to QRS waves, the T waves have the largest amplitude and the closest morphology to the complexes of QRS over the entire cardiac cycle, so that it is sometimes difficult to determine, and thus it is difficult to accurately distinguish the T waves from the QRS waves. As shown in fig. 1 and fig. 2, the circled T wave in fig. 1 is a high T wave, and the circled T wave in fig. 2 is a T wave with an amplitude very close to that of the QRS wave. Therefore, for the situation shown in fig. 1 and fig. 2, the conventional QRS wave detecting method cannot accurately distinguish the QRS wave from the T wave, and cannot accurately detect the QRS wave. Therefore, the embodiment of the present application provides a QRS wave detection method, which performs initial QRS wave detection on an acquired ECG signal, that is, an electrocardiographic signal, and then performs cluster analysis on the initially pre-detected QRS wave, that is, separates two types of signals as much as possible by means of statistics. According to the correlation of the two types of signals, the decomposition layer number and the target detection threshold value of the wavelet are set in a self-adaptive mode, then the obtained QRS waves are decomposed based on the decomposition layer number of the wavelet, the decomposed QRS waves are further detected based on the determined target detection threshold value, therefore, the target QRS waves and the T waves can be accurately determined, and the QRS wave detection accuracy is greatly improved.
The embodiment of the application provides a method for detecting QRS waves, which specifically includes the following steps as shown in fig. 3:
step S101, clustering wavelet signals at each position to be detected in electrocardiosignals to be detected to obtain a plurality of wavelet sets;
in the specific implementation process of the step, the QRS wave pre-detection processing can be performed on the original electrocardiosignals, so that a plurality of positions to be detected, which may be QRS waves, can be determined, and then clustering processing is performed.
Step S102, under the condition that the number of the wavelet sets is two, performing signal decomposition on each wavelet signal in the two wavelet sets to obtain a wavelet signal after signal decomposition;
in this step, a wavelet decomposition method may be specifically used to decompose each wavelet signal in the two wavelet sets, so as to obtain a wavelet signal after signal decomposition. Specifically, when wavelet decomposition is performed, the number of decomposition layers can be set according to actual needs.
Step S103, determining a target detection threshold value based on the decomposed wavelet signals;
in this step, after the decomposed wavelet signals are obtained, the target detection threshold may be determined based on each decomposed wavelet signal, for example, the wavelet signal with the largest modulus maximum of the decomposed wavelet signals in the predetermined period and the wavelet signal with the smallest modulus maximum in the predetermined period may be determined, and the target detection threshold may be calculated using the wavelet signal with the largest modulus maximum and the wavelet signal with the smallest modulus maximum in the predetermined period. The modulus maximum in this step represents the amplitude of the signal.
And step S104, detecting each decomposed wavelet signal based on the target detection threshold value, and determining a target QRS wave.
After the target detection threshold is obtained in this step, each decomposed wavelet signal may be determined based on the target detection threshold, so as to determine that the wavelet signal that meets the target detection threshold is a target QRS wave, and the wavelet signal that does not meet the target detection threshold is a T wave.
In the embodiment of the application, after clustering processing is performed on the wavelet signals at each position to be detected in the electrocardiosignals to be detected, if 1 wavelet set is obtained, the wavelet signals at each position to be detected in the set can be directly determined as the target QRS wave. If the number of the wavelet sets is greater than 2, for example, 3 wavelet sets are obtained, it is determined that the wavelet signals at the positions to be detected are non-QRS waves, that is, the wavelet signals in the 3 wavelet sets are subjected to great noise interference, so that the wavelet signals at the positions to be detected can be marked as noise.
The method and the device have the advantages that the pre-detected QRS waves are clustered, then the two types of signals obtained by clustering are subjected to signal decomposition, and the detection threshold value is re-determined, so that the pre-detected QRS waves can be further detected, the target QRS waves and the interference waves can be accurately determined from the pre-detected QRS waves, and the QRS wave detection accuracy is improved.
Another embodiment of the present application provides a method for detecting QRS waves, as shown in fig. 4, including the following steps:
step S201, sequentially carrying out filtering processing and difference processing on the original electrocardiosignals to obtain processed electrocardiosignals to be detected; and carrying out QRS wave pre-detection processing on the electrocardiosignals to be detected based on the initial detection threshold value so as to determine a plurality of positions to be detected.
In this step, when implemented, the following method may be specifically adopted to perform QRS wave pre-detection processing, as shown in fig. 5, including: the input ECG signal is preprocessed and filtered by a low-pass filter and a high-pass filter, respectively, so that frequency signals other than QRS waves can be attenuated as much as possible. Because the overall slope of the QRS wave is usually greater than that of other waves, the first-order difference processing needs to be performed on the filtered signal, so that the QRS wave signal can be highlighted effectively, and then the QRS wave position determination is performed on the differentiated signal by using a preset initial detection threshold value, so that a plurality of positions to be detected are obtained.
Step S202, clustering wavelet signals at each position to be detected in the electrocardiosignals to be detected to obtain a plurality of wavelet sets;
in this step, after each position to be detected is determined, wavelet signals of each position to be detected may be obtained first, that is, pre-detected QRS wave signals are obtained, then data of a section of approximately one heart beat centered on each pre-detected QRS is obtained, then characteristic parameters such as amplitude, slope and the like of each pre-detected QRS wave signal are obtained, screening is performed according to a preset threshold value to remove some mutation points, and finally, cluster analysis is performed on the screened pre-detected QRS wave signals to obtain a plurality of wavelet sets.
Step S203, under the condition that the number of the wavelet sets is two, performing signal decomposition on each wavelet signal in the two wavelet sets to obtain a wavelet signal after signal decomposition;
in this step, when two types of signals are obtained by classification, it can be preliminarily determined that one type is a QRS wave signal, and the other type may be a T wave signal. And the closer to the QRS wave, the more difficult the processing, therefore, after identifying the two types of signals, the similarity of the two types of signals can be further determined, so as to determine the decomposition layer number for signal decomposition. I.e. determining the wavelet signal similarity of two wavelet sets and then determining the number of decomposition levels for performing the signal decomposition based on said wavelet signal similarity. Therefore, the number of layers of signal decomposition is more reasonable, the calculation amount is reduced as far as possible on the premise that the QRS waves and the T waves can be accurately distinguished, and the detection efficiency is improved.
After the number of decomposition layers is determined, performing wavelet decomposition processing on the electrocardiosignal to be detected based on the determined number of decomposition layers; and acquiring wavelet signals at each position to be detected in the electrocardiosignals to be detected after wavelet decomposition processing so as to obtain the wavelet signals after signal decomposition.
Step S204, determining a target detection threshold value based on the decomposed wavelet signals;
when the target detection threshold is determined, the wavelet signals meeting the conditions are selected from the decomposed wavelet signals, and then the target detection threshold is calculated and obtained according to the selected wavelet signals and the similarity of the wavelet signals of the two wavelet sets, so that the determination of the target detection threshold is more reasonable and accurate, and the guarantee is provided for the subsequent accurate detection of the target QRS wave.
Step S205, detecting each decomposed wavelet signal based on the target detection threshold, and determining a target QRS wave.
In this step, after the target detection threshold is obtained, the decomposed wavelet signals can be detected based on the target detection threshold, so as to accurately distinguish the target QRS wave and the T wave.
According to the method, the original electrocardiosignals are preprocessed, so that a plurality of pre-detected QRS waves are obtained, the pre-detected QRS waves are clustered, then two types of signals obtained by clustering are subjected to signal decomposition, and a target detection threshold value is re-determined, so that the pre-detected QRS waves can be further detected based on the target detection threshold value, the target QRS waves and interference waves are accurately determined from the pre-detected QRS waves, and the QRS wave detection accuracy is improved.
Another embodiment of the present application provides a method for detecting QRS waves, as shown in fig. 6, including the following steps:
step S301, sequentially carrying out filtering processing and difference processing on the original electrocardiosignals to obtain processed electrocardiosignals to be detected; and carrying out QRS wave pre-detection processing on the electrocardiosignals to be detected based on the initial detection threshold value so as to determine a plurality of positions to be detected.
Step S302, clustering wavelet signals at each position to be detected in the electrocardiosignals to be detected to obtain a plurality of wavelet sets;
step S303, under the condition that the number of the wavelet sets is two, respectively calculating signal parameter average values based on the signal parameters of the wavelet signals in the wavelet sets to obtain average wavelet signals corresponding to the wavelet sets; signal correlation is calculated based on the average wavelet signals corresponding to each wavelet set to determine wavelet signal similarity for the two wavelet sets.
In this step, the signal parameters specifically include the amplitude of the signal, that is, in this step, the average value of the amplitudes of the wavelet signals corresponding to the wavelet sets is calculated according to the amplitudes of the wavelet signals, and then the signal correlation is calculated by using the average value of the amplitudes of the wavelet signals corresponding to the two wavelet sets. When the signal correlation is calculated, the calculation may be specifically performed by using a pearson correlation coefficient calculation method.
Step S304, determining the decomposition layer number for signal decomposition based on the wavelet signal similarity.
In the present application, by performing wavelet decomposition on wavelet signals, the signals can be decomposed on different frequency bands, and in principle, the frequency bands of the T wave and the QRS wave are not completely on one frequency band, but when the two signals are close to each other, a certain frequency band may be overlapped. Therefore, if the decomposition level is increased, the signal decomposition can be more detailed, and the interference of the T wave can be more accurately removed. But the more levels of decomposition, the more computation. As shown in FIGS. 7(a) and 7(b), FIG. 7(a) is a 2-layer decomposition of the original signal, i.e., d 2 And d 1 FIG. 7(b) is a diagram with 4 layers, d, exploded 4 -d 1 It is clear that the layer 3 d with a higher SNR can be chosen on the basis of the decomposition of the 4 layers 2 Or layer 4 d 1 And (6) processing. In order to balance the relationship between the calculation accuracy and the calculation complexity, the appropriate number of decomposition layers is determined according to the similarity of the QRS waves and the T waves, so that the QRS waves and the T waves can be accurately distinguished, and meanwhile, the calculation amount is reduced. In this embodiment, the following calculation formula may be specifically adopted when calculating the number of decomposition layers:
decomposition layer number ═ ceil (2.07 × exp (abs (corrcoef)) +1)
Wherein ceil represents rounding up; exp represents an exponentiation function; abs represents the absolute value, corrcoef represents the correlation coefficient, i.e. the wavelet signal similarity. In this embodiment, the maximum number of decomposition layers is 7, and the minimum number of decomposition layers is 4, thereby ensuring the accuracy of QRS wave detection.
Step S305, performing wavelet decomposition processing on the electrocardiosignal to be detected based on the determined decomposition layer number; and acquiring wavelet signals at each position to be detected in the electrocardiosignals to be detected after wavelet decomposition processing so as to obtain the wavelet signals after signal decomposition.
Step S306, acquiring wavelet signals of each position to be detected in a preset time period from the electrocardiosignals to be detected after the signal decomposition processing, and taking the wavelet signals as first wavelet signals; determining a plurality of wavelet signals meeting a first condition from the first wavelet signals as second wavelet signals; determining a plurality of wavelet signals meeting a second condition from the first wavelet signals as third wavelet signals; and calculating and obtaining the target detection threshold value based on each second wavelet signal and each third wavelet signal.
When this step is performed, the first condition is: sorting the modulus maxima of the first wavelet signals according to a sorting order from large to small, and then sorting the first wavelet signals positioned at the front n; the second condition is: sorting the modulus maxima of the first wavelet signals according to a sorting order from large to small, and then sorting the first wavelet signals positioned at the back n; wherein n is less than one-half of the total number of the first wavelet signals and n is greater than or equal to 1.
The predetermined time period and n may be set according to actual needs, and the predetermined time period is 6s, and n is 8 in the present application. After wavelet decomposition processing is performed on each wavelet signal based on the decomposition layer number to obtain a wavelet signal after signal decomposition, it is necessary to calculate the modulus maximum of each wavelet signal first, that is, calculate the amplitude of each wavelet signal, then take the modulus maximum of the wavelet signal in the front 6s, and then sort the modulus maxima of the wavelet signals in the 6s from large to small, and as a whole, after wavelet decomposition, because the slope of the QRS wave is higher than that of the T wave, the modulus maximum of the QRS wave is generally higher than that of the T wave, and therefore, the median of the modulus maxima of the wavelet signals in the front 8 in the arrangement order is taken as a signal, thereby obtaining a second wavelet signal. Then, the median of the mode maximum of the wavelet signals positioned at the rear 8 in the arrangement sequence is taken as a noise signal, so that a third wavelet signal is obtained, and finally, the wavelet signal similarity of the two wavelet sets, the second wavelet signal and the third wavelet signal are used for calculating a target detection threshold value, so that the detection threshold value is updated. Therefore, the interference of T wave can be greatly avoided. The calculation formula of the target detection threshold in this embodiment is as follows:
cmpth＝peak s *coef-peak n *(1-coef)
wherein cmpth represents a target detection threshold; peak is a product of s Representing a signal peak, i.e., a second wavelet signal; coef represents a correlation coefficient, namely representing wavelet signal similarity; peak is a product of n Representing a noise peak, i.e. representing the third wavelet signal.
Step S305, detecting each decomposed wavelet signal based on the target detection threshold, and determining a target QRS wave.
In this step, after the target detection threshold is obtained, the decomposed wavelet signals can be detected based on the target detection threshold, so as to accurately distinguish the target QRS wave from the T wave. Fig. 8 is a schematic diagram of QRS wave detection on decomposed wavelet signals by calculating a target detection threshold according to similarity of wavelet signals by using the method of the present application, and fig. 9 is a schematic diagram of QRS wave detection on wavelet signals by using a fixed detection threshold in the conventional method. Comparing the two results, it can be seen that, in fig. 9, since the fixed detection threshold is used for detection, the interference wave at the point c in fig. 9 is detected as a QRS wave, and the QRS wave at the point d is missed, so that the detection result is not accurate enough. In fig. 8, curve a is a target detection threshold curve, and it can be seen from fig. 8 that the interference waves at point a can be screened out, and the QRS waves at point b can be detected. Therefore, QRS waves can be accurately detected, interference waves T waves are screened and deleted, and the QRS waves are more accurately detected.
Because T wave interference is large, the method and the device classify the T wave and the QRS as basic processing according to the conditions of the T wave and the QRS, and therefore the problem of large T wave interference is effectively solved. In addition, the self-adaptive wavelet decomposition level is set according to the relevant conditions of the T wave and the QRS, so that the accuracy is ensured, and the calculation efficiency is saved. In addition, according to the correlation condition of the T wave and the QRS, the modulus maximum value threshold value is set in a self-adaptive mode, so that the QRS wave is effectively detected, and meanwhile, the interference of noise is reduced.
Another embodiment of the present application provides a QRS wave detection apparatus, as shown in fig. 10, including:
the clustering module 1 is used for clustering wavelet signals at each position to be detected in the electrocardiosignals to be detected to obtain a plurality of wavelet sets;
the signal decomposition module 2 is used for performing signal decomposition on each wavelet signal in the two wavelet sets under the condition that the number of the wavelet sets is two, and obtaining a wavelet signal after signal decomposition;
a determining module 3, configured to determine a target detection threshold based on the decomposed wavelet signal;
and the detection module 4 is configured to detect each decomposed wavelet signal based on the target detection threshold, and determine a target QRS wave.
The QRS wave detection apparatus in this implementation further includes a pre-detection module, the pre-detection module is configured to: sequentially carrying out filtering processing and differential processing on the original electrocardiosignals to obtain processed electrocardiosignals to be detected; and carrying out QRS wave pre-detection processing on the electrocardiosignals to be detected based on the initial detection threshold value so as to determine a plurality of positions to be detected.
The QRS wave detection apparatus in this implementation further includes a decomposition layer number determining module, where the decomposition layer number determining module is configured to: determining the wavelet signal similarity of the two wavelet sets; determining a number of decomposition levels for performing signal decomposition based on the wavelet signal similarities.
Specifically, the decomposition layer number determining module is specifically configured to: the determining the wavelet signal similarity of the two wavelet sets specifically includes:
respectively calculating signal parameter average values based on signal parameters of all wavelet signals in the wavelet set to obtain average wavelet signals corresponding to the wavelet set; and calculating signal correlation based on the average wavelet signals corresponding to the wavelet sets to determine the wavelet signal similarity of the two wavelet sets.
The signal decomposition module in this embodiment is specifically configured to: performing wavelet decomposition processing on the electrocardiosignal to be detected based on the determined decomposition layer number; and acquiring wavelet signals at each position to be detected in the electrocardiosignals to be detected after wavelet decomposition processing so as to obtain the wavelet signals after signal decomposition.
In an implementation process, the determining module in this embodiment is specifically configured to: acquiring wavelet signals of each position to be detected in a preset time period from the electrocardiosignals to be detected after signal decomposition processing, and taking the wavelet signals as first wavelet signals; determining a plurality of wavelet signals meeting a first condition from the first wavelet signals as second wavelet signals; determining a plurality of wavelet signals meeting a second condition from the first wavelet signals as third wavelet signals; and calculating and obtaining the target detection threshold value based on each second wavelet signal and each third wavelet signal. Wherein the first condition is: sorting the modulus maxima of the first wavelet signals according to a sorting order from large to small, and then sorting the first wavelet signals positioned at the front n; the second condition is: sorting the modulus maxima of the first wavelet signals according to a sorting order from large to small, and then sorting the first wavelet signals positioned at the back n; wherein n is less than one-half of the total number of the first wavelet signals and n is greater than or equal to 1.
The QRS wave detection apparatus in this embodiment further includes a determination module, where the determination module is configured to determine, when the number of the wavelet sets is 1, that the wavelet signal at each position to be detected is a target QRS wave; and under the condition that the number of the wavelet sets is more than 2, determining that the wavelet signals at the positions to be detected are non-QRS waves.
This application is through clustering the QRS ripples that detects in advance, then carries out signal decomposition to two kinds of signals that the cluster obtained to the redetermination detects the threshold value, and then can carry out further detection to the QRS ripples that detects in advance to accurate target QRS ripples and interference wave of confirming in the QRS ripples that detects in advance, improved the rate of accuracy that QRS ripples detected.
Yet another embodiment of the present application provides an electronic device, which at least includes a memory and a processor, where the memory stores a computer program thereon, and the processor implements the following steps when executing the computer program on the memory:
step one, clustering wavelet signals at positions to be detected in electrocardiosignals to be detected to obtain a plurality of wavelet sets;
secondly, under the condition that the number of the wavelet sets is two, performing signal decomposition on each wavelet signal in the two wavelet sets to obtain a wavelet signal after signal decomposition;
thirdly, determining a target detection threshold value based on the decomposed wavelet signals;
and fourthly, detecting each decomposed wavelet signal based on the target detection threshold value to determine a target QRS wave.
The specific implementation process of the above method steps can refer to the steps of the QRS wave detection method in any of the above embodiments, and the description of this embodiment is not repeated here.
This application is through clustering the QRS ripples that detects in advance, then carries out signal decomposition to two kinds of signals that the cluster obtained to the redetermination detects the threshold value, and then can carry out further detection to the QRS ripples that detects in advance to accurate target QRS ripples and interference wave of confirming in the QRS ripples that detects in advance, improved the rate of accuracy that QRS ripples detected.
The above embodiments are only exemplary embodiments of the present application, and are not intended to limit the present application, and the protection scope of the present application is defined by the claims. Various modifications and equivalents may be made by those skilled in the art within the spirit and scope of the present application and such modifications and equivalents should also be considered to be within the scope of the present application.
Claims (9)
1. A QRS wave detection method comprises the following steps:
clustering wavelet signals at each position to be detected in the electrocardiosignals to be detected to obtain a plurality of wavelet sets;
under the condition that the number of the wavelet sets is two, performing signal decomposition on each wavelet signal in the two wavelet sets to obtain a wavelet signal after the signal decomposition; prior to signal decomposing each wavelet signal in the two wavelet sets, the method further comprises:
determining the wavelet signal similarity of the two wavelet sets;
determining the number of decomposition layers for signal decomposition based on the wavelet signal similarity;
determining a target detection threshold based on the decomposed wavelet signals;
and detecting each decomposed wavelet signal based on the target detection threshold value to determine a target QRS wave.
2. The method according to claim 1, before clustering the wavelet signals at each position to be detected in the electrocardiographic signals to be detected, the method further comprises:
sequentially carrying out filtering processing and differential processing on the original electrocardiosignals to obtain processed electrocardiosignals to be detected;
and carrying out QRS wave pre-detection processing on the electrocardiosignals to be detected based on the initial detection threshold value so as to determine a plurality of positions to be detected.
3. The method of claim 1, wherein said determining wavelet signal similarity for two wavelet sets specifically comprises:
respectively calculating signal parameter average values based on signal parameters of all wavelet signals in the wavelet set to obtain average wavelet signals corresponding to the wavelet set;
signal correlation is calculated based on the average wavelet signals corresponding to each wavelet set to determine wavelet signal similarity for the two wavelet sets.
4. The method of claim 1, wherein performing signal decomposition on each wavelet signal in the two wavelet sets to obtain a signal-decomposed wavelet signal, specifically comprises:
performing wavelet decomposition processing on the electrocardiosignal to be detected based on the determined decomposition layer number;
and acquiring wavelet signals at each position to be detected in the electrocardiosignals to be detected after wavelet decomposition processing so as to obtain the wavelet signals after signal decomposition.
5. The method of claim 1, wherein determining a target detection threshold based on the decomposed wavelet signals comprises:
acquiring wavelet signals of each position to be detected in a preset time period from the electrocardiosignals to be detected after the signal decomposition processing, and taking the wavelet signals as first wavelet signals;
determining a plurality of wavelet signals meeting a first condition from the first wavelet signals as second wavelet signals;
determining a plurality of wavelet signals meeting a second condition from the first wavelet signals as third wavelet signals;
and calculating and obtaining the target detection threshold value based on each second wavelet signal and each third wavelet signal.
6. The method of claim 5, wherein the first condition is: sorting the modulus maxima of the first wavelet signals according to a sorting order from large to small, and then sorting the first wavelet signals positioned at the top n;
the second condition is that: sorting the modulus maxima of the first wavelet signals according to a sorting order from large to small, and sorting the first wavelet signals positioned at the back n; wherein n is less than one-half of the total number of the first wavelet signals and n is greater than or equal to 1.
7. The method of claim 1, in the case where the number of wavelet sets is 1, the method further comprising: determining wavelet signals at positions to be detected as target QRS waves;
in the case that the number of the wavelet sets is greater than 2, the method further comprises: and determining the wavelet signals at the positions to be detected as non-QRS waves.
8. A QRS wave detecting apparatus, comprising:
the clustering module is used for clustering wavelet signals at each position to be detected in the electrocardiosignals to be detected to obtain a plurality of wavelet sets;
the signal decomposition module is used for performing signal decomposition on each wavelet signal in the two wavelet sets under the condition that the number of the wavelet sets is two to obtain a wavelet signal after the signal decomposition; before signal decomposition is performed on each wavelet signal in the two wavelet sets, the method further comprises:
determining wavelet signal similarity of the two wavelet sets;
determining the number of decomposition layers for signal decomposition based on the wavelet signal similarity;
a determining module for determining a target detection threshold based on the decomposed wavelet signals;
and the detection module is used for detecting each decomposed wavelet signal based on the target detection threshold value to determine a target QRS wave.
9. An electronic device comprising at least a memory, a processor, the memory having a computer program stored thereon, wherein the processor, when executing the computer program on the memory, is adapted to carry out the steps of the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011339363.XA CN113229826B (en) | 2020-11-25 | 2020-11-25 | QRS wave detection method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011339363.XA CN113229826B (en) | 2020-11-25 | 2020-11-25 | QRS wave detection method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113229826A CN113229826A (en) | 2021-08-10 |
| CN113229826B true CN113229826B (en) | 2022-07-26 |
Family
ID=77130015
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011339363.XA Active CN113229826B (en) | 2020-11-25 | 2020-11-25 | QRS wave detection method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113229826B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115956925B (en) * | 2023-02-10 | 2023-06-06 | 合肥心之声健康科技有限公司 | QRS wave detection method and system based on multistage smooth envelope |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10779744B2 (en) * | 2015-10-27 | 2020-09-22 | Cardiologs Technologies Sas | Automatic method to delineate or categorize an electrocardiogram |
| CN106214123B (en) * | 2016-07-20 | 2019-01-25 | 杨一平 | A kind of electrocardiogram compressive classification method based on deep learning algorithm |
| CN108509823A (en) * | 2017-02-24 | 2018-09-07 | 深圳市理邦精密仪器股份有限公司 | The detection method and device of QRS complex |
| CN107622259B (en) * | 2017-10-20 | 2019-12-24 | 山东大学 | T wave detection method, electrocardiogram data analysis method and device |
| CN108056773A (en) * | 2017-12-11 | 2018-05-22 | 重庆邮电大学 | Based on the algorithms of QRS complexes detection in electrocardiogram signal for improving variation mode decomposition |
-
2020
- 2020-11-25 CN CN202011339363.XA patent/CN113229826B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113229826A (en) | 2021-08-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Meyer et al. | Combining algorithms in automatic detection of QRS complexes in ECG signals | |
| CN110013247B (en) | Detection, differentiation and positioning method for electrocardiogram P wave and T wave | |
| Shyu et al. | Using wavelet transform and fuzzy neural network for VPC detection from the Holter ECG | |
| CN103110417B (en) | Automatic electrocardiogram recognition system | |
| CN109758145B (en) | Automatic sleep staging method based on electroencephalogram causal relationship | |
| CN109948396B (en) | Heart beat classification method, heart beat classification device and electronic equipment | |
| CN103860162A (en) | Pace-making signal detecting method and system and electrocardio detecting device | |
| CN111481192B (en) | Electrocardiosignal R wave detection method based on improved U-Net | |
| US11638562B2 (en) | Brain activity analysis method and apparatus thereof | |
| Dotsinsky et al. | Ventricular beat detection in single channel electrocardiograms | |
| CN110680302A (en) | Automatic identification method for electrocardiosignal characteristic wave | |
| CN101449973A (en) | Judgment index generation method and device for cardiac interference signal identification | |
| CN107233093B (en) | R wave detection method and device and electronic equipment | |
| Wróbel et al. | Improving fetal heart rate signal interpretation by application of myriad filtering | |
| CN110522442B (en) | Multi-lead electrocardiographic abnormality detection device, electronic apparatus, and storage medium | |
| Kumar et al. | Performance analysis of different filters for power line interface reduction in ECG signal | |
| CN108888259A (en) | A kind of real-time QRS wave detection method of electrocardiosignal | |
| CN115120248B (en) | Histogram-based adaptive threshold R peak detection and heart rhythm classification method and device | |
| CN111358459A (en) | Arrhythmia identification method, device, equipment and storage medium | |
| Belkadi et al. | A robust QRS detection approach using stationary wavelet transform | |
| CN113229826B (en) | QRS wave detection method and device and electronic equipment | |
| CN115486814A (en) | Intelligent fusion analysis and processing method based on multi-modal epilepsy data | |
| CN108694355B (en) | Signal processing method and device | |
| CN115486849A (en) | Electrocardiosignal quality evaluation method, device and equipment | |
| Tun et al. | Analysis of computer aided identification system for ECG characteristic points |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |